Reinforcement learning algorithms: A brief survey

Shakya, Ashish Kumar; Pillai, G. N.; Chakrabarty, Sohom

doi:10.1016/j.eswa.2023.120495

Cited by 106 publications

(16 citation statements)

References 179 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The actions taken by the agent are guided by either trial-and-error, or based on the state of the environment and rewards, or a combination of both. By performing these actions iteratively, the agent learns an optimal behavioral strategy based on the rewards received from previous interactions [49].…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…Reinforcement Learning (RL) is a machine learning technique to learn sequential decision-making in complex scenarios [49]. RL is inspired by trial-and-error based human/animal learning, wherein the learning is driven by a scaler quantity (the ‘reinforcement’ or the ‘reward’) and the goal of the algorithm is to maximize the expected future cumulative reward [50].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing sequential gene expression modulation for cellular reprogramming - Coupled Boolean modeling and Reinforcement Learning based method

Singh

2024

Preprint

View full text Add to dashboard Cite

Regenerative medicine entails regenerating damaged cells and tissues from healthy cells through the process of cellular reprogramming. The most common method to achieve reprogramming of cells of one type to another is by modulating the activity of specific genes. However, identifying the most suitable genes for reprogramming is a challenge due to their large number in humans and their complex interactions. This study describes a computational method to predict sequential gene expression modulation for reprogramming a starting cell type to a target cell type. The proposed method integrates: (1) a Boolean model of the concerned gene regulatory network (GRN); and (2) a reinforcement learning (RL) based model for optimization. The Boolean model is used to capture the dynamic behavior of the GRN and to understand how the gene expression modulation alters its behavior. RL model is used to optimize sequential decision-making of predicting the suitable sequence of gene expression modulation. Coupling of the Boolean model and RL plays a crucial role in the proposed computational method. Boolean model captures the GRN dynamics, and thereby, constrains the combinatorially large state space. The RL model operates in this constrained state space and uses the Boolean model to evaluate the effect of modulations on GRN dynamics to predict the sequence of suitable gene expression modulations. Applicability of the proposed method is demonstrated using a toy network of 4 genes, and a biological network of heart development representing the dynamics of 15 genes.

show abstract

Section: Reinforcement Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimizing sequential gene expression modulation for cellular reprogramming - Coupled Boolean modeling and Reinforcement Learning based method

Singh

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The key feature of Q-learning is that it estimates the action-value function Q which leads to directly approximating q * (the optimal action-value function), regardless of the policy being executed [58,59]. This technique is defined in Equation ( 24) as follows:…”

Section: Q-learningmentioning

confidence: 99%

“…As mentioned in the previous section, temporal difference learning is a combination of the ideas of both Monte Carlo and dynamic programming. Therefore, the TD algorithm learns from experience where there is an unknown model or no model of the environment’s dynamic, similar to MC [ 58 ]. On the other way, TD, like DP algorithms, updates estimates depending on the other learned estimates without waiting for a whole episode to be finished.…”

Section: Reinforcement Learning (Rl)mentioning

confidence: 99%

“…Q-learning is a widely recognized off-policy algorithm in reinforcement learning (RL). The key feature of Q-learning is that it estimates the action-value function Q which leads to directly approximating

(the optimal action-value function), regardless of the policy being executed [ 58 , 59 ]. This technique is defined in Equation (24) as follows:

where the Q-learning updates use only the four elements

while assuming

is a decision variable to optimize the action-value function.…”

Section: Reinforcement Learning (Rl)mentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning Algorithms and Applications in Healthcare and Robotics: A Comprehensive and Systematic Review

Al-Hamadani,

Fadhel,

Alzubaidi

et al. 2024

Sensors

View full text Add to dashboard Cite

Reinforcement learning (RL) has emerged as a dynamic and transformative paradigm in artificial intelligence, offering the promise of intelligent decision-making in complex and dynamic environments. This unique feature enables RL to address sequential decision-making problems with simultaneous sampling, evaluation, and feedback. As a result, RL techniques have become suitable candidates for developing powerful solutions in various domains. In this study, we present a comprehensive and systematic review of RL algorithms and applications. This review commences with an exploration of the foundations of RL and proceeds to examine each algorithm in detail, concluding with a comparative analysis of RL algorithms based on several criteria. This review then extends to two key applications of RL: robotics and healthcare. In robotics manipulation, RL enhances precision and adaptability in tasks such as object grasping and autonomous learning. In healthcare, this review turns its focus to the realm of cell growth problems, clarifying how RL has provided a data-driven approach for optimizing the growth of cell cultures and the development of therapeutic solutions. This review offers a comprehensive overview, shedding light on the evolving landscape of RL and its potential in two diverse yet interconnected fields.

show abstract

Non‐overlapping placement of macro cells based on reinforcement learning in chip design

Yu,

Gao,

Wang

et al. 2024

Circuit Theory & Apps

View full text Add to dashboard Cite

Due to the increasing complexity of chip design, existing placement methods still have many shortcomings in dealing with macro cells coverage and optimization efficiency. Aiming at the problems of layout overlap, inferior performance, and low optimization efficiency in existing chip design methods, this paper proposes an end‐to‐end placement method, SRLPlacer, based on reinforcement learning. First, the placement problem is transformed into a Markov decision process by establishing the coupling relationship graph model between macro cells to learn the strategy for optimizing layouts. Secondly, the whole placement process is optimized after integrating the standard cell layout. By assessing the public benchmark ISPD2005, the proposed SRLPlacer can effectively solve the overlap problem between macro cells while considering routing congestion and shortening the total wire length to ensure routability.

show abstract

Reinforcement learning algorithms: A brief survey

Cited by 106 publications

References 179 publications

Optimizing sequential gene expression modulation for cellular reprogramming - Coupled Boolean modeling and Reinforcement Learning based method

Optimizing sequential gene expression modulation for cellular reprogramming - Coupled Boolean modeling and Reinforcement Learning based method

Reinforcement Learning Algorithms and Applications in Healthcare and Robotics: A Comprehensive and Systematic Review

Non‐overlapping placement of macro cells based on reinforcement learning in chip design

Contact Info

Product

Resources

About